David Golden

Senior Staff Engineer (ex Director) @ MongoDB. I like building things, solving problems and playing games, occasionally at the same time. Opinions are my own.

[David Golden @xdg]

One of the skills of a great software developer is being able to read code you’ve just written with the eyes of someone who isn't intimately familiar with it.

[David Golden @xdg]

@swyx "Thoughts?" is my usual go to.

[David Golden @xdg]

@GergelyOrosz It's not mind boggling. Everyone knows it's terrible, but it's readily available and easy. Streetlight Effect.

[Anthropic @AnthropicAI]

Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor.

It’s happening faster than we thought, and the implications deserve greater attention. https://t.co/OVVPJO7VQx

[David Golden @xdg]

This.

[Phil Eaton @eatonphil]

AI makes good programmers 10x better: you can easily understand and contribute to more codebases and actually make an impact.

AI makes bad programmers 10x worse: you generate loads of garbage code and tests that everyone else has to understand and wade through.

[David Golden @xdg]

@ejames_c Load-bearing

[Eugene Yan @eugeneyan]

some thoughts on working with ai models

• context as infra
• taste as config
• verification for autonomy
• scaling via delegation
• closing the loop

https://t.co/pdd8bk66Jz

[David Golden @xdg]

I agree, which is why I think Mythos is effective at challenging the "impossibile" frame. The thought experiment is: "Imagine someone who sees a continuous exponential trend from vibeslop a year ago, to Opus 4.5 at year end, to Mythos and beyond. What do you think *they* might believe about the future of the SDLC in the next year or two?"

It doesn't require shifting one's own view, only being able to model someone else's. Many people won't, of course. And even if one models the other group, one doesn't have to accept the frame. But I'd like to think that an intellectually honest person would then be prompted to articulate the evidence that keeps them in the existing frame and triggers that would cause them to reconsider.

[David Golden @xdg]

@ejames_c FWIW, I've found Mythos-class models to be a useful intuition pump. A model that finds 0-days better than humans challenges the group A frame. If the next 6-12 months brings new models that can review code better than humans, what then is the role of humans in the SDLC?

[David Golden @xdg]

@Swizec @eugeneyan I'm laughing tonight, but I like @eugeneyan too much to say why. But I know he knows. 😆

[David Golden @xdg]

@TheZvi At work, I've started using the phrase "Mythos-class models" to signal that the category shift is the important thing to prepare for.

[Eugene Yan @eugeneyan]

excited to share this and help everyone be more cyber secure

[David Golden @xdg]

@GergelyOrosz Time to repost your A, B, C comp distribution. Given the quoted comp includes equity, $570k isn't even that high.

[David Golden @xdg]

@staysaasy Once again, I feel seen. 😆

[David Golden @xdg]

@TheZvi It's a real issue. Mine have been anti-AI indoctrinated by their school to the point where they aren't developing success skills. (Assuming non-doom futures, but 🤷)

[David Golden @xdg]

@TheZvi Also, changing the Claude Code default effort to 'xhigh' -- doubling token usage -- is pretty despicable.

[David Golden @xdg]

@TheZvi Same progression from 4.5 to 4.6 of more utility but less engaging. Too quick to leap into action when it should discuss options. Subtly needs more nudges and course correction. Too literal with instructions. In creating a model that will grind for hours, they lost something.

[David Golden @xdg]

Anthropic ARR soaring!

Also, Claude Code default effort with Opus 4.7 changed from 'medium' to 'xhigh' resulting in double token usage.

Also, 1 mil context windows rolled out, with O(n^2) cost.

Also, Enterprise contracts switched to usage-based pricing months ago.

💰💰💰

[David Golden @xdg]

@bcherny @GergelyOrosz Today Chat would not even open a URL I provided. Search is on. I filled a support ticket. (Enterprise plan.)

I agree with Gergely. I'd be happier with fewer new features and more uptime.

[David Golden @xdg]

@bcherny Auto mode for Max plans when?!?

I get that it costs extra tokens, but I'm happy for it to use my token budget faster if I can get more done.

[David Golden @xdg]

@staysaasy I'm seeing multiple cases of people writing an internal CRUD app instead of sharing spreadsheets. Not quite the same thing but a lot of SaaS apps are fancy spreadsheet replacers anyway.